Research map / Architectures and efficiency / CNN design
Auto-Balanced Filter Pruning for Efficient Convolutional Neural Networks
Read the paperCheck your idea against 108,967 papers
AI-extracted summary. Written by AI from the paper's title only (no summary yet). Numbers and claims can be wrong or missing context, so check the paper before you cite or build on it.
Measured effects reported in the paper
| What was changed | Where | Measured | Effect |
|---|---|---|---|
| add auto-balanced regularization pre-training (ablation) | Abreast Advancing filter pruning · CIFAR-10 VGG-16 (79.69% FLOPs pruned) | error %: 7.28 -> 7.06 | Helped |
| add auto-balanced regularization pre-training (ablation) | Abreast Advancing filter pruning · CIFAR-10 VGG-16 (81.39% FLOPs pruned) | error %: 7.56 -> 7.13 | Helped |
| AFP filter pruning | LeNet-5 · MNIST | error %: 0.83 -> 0.76 | Helped |
| AFP filter pruning (60.86% FLOPs) | ResNet-56 · CIFAR-10 | error %: 6.07 -> 7.06 | Hurt |
| prune more aggressively (q=12,16,16) (ablation) | AFP on ResNet-56 · CIFAR-10 | error %: 7.06 -> 9.43 | Hurt |
Closest papers by meaning
- Pruning Filters for Efficient ConvNets (ICLR 2017 · similarity 0.92)
- Provable Filter Pruning for Efficient Neural Networks (ICLR 2020 · similarity 0.91)
- Compressing Convolutional Neural Networks via Factorized Convolutional Filters (CVPR 2019 · similarity 0.91)
- DPFPS: Dynamic and Progressive Filter Pruning for Compressing Convolutional Neural Networks from Scratch (AAAI 2021 · similarity 0.91)
- Interspace Pruning: Using Adaptive Filter Representations To Improve Training of Sparse CNNs (CVPR 2022 · similarity 0.91)
- Entropy Induced Pruning Framework for Convolutional Neural Networks (AAAI 2024 · similarity 0.89)
Writing a paper in this area? scime draft is a free LaTeX editor with AI included, real-time co-authors and a check of your references and venue rules before you submit. It also imports OpenAI Prism projects.